EDA Assignment - Some details about India in Graphs

knitr::opts_chunk$set(
    fig.align = "center",
    fig.height = 9,
    fig.width = 14,
    message = FALSE,
    warning = FALSE
)
library(dplyr)
library(ggplot2)
options(scipen = 999)
library(ggthemes)
library(plotly)
library(readxl)
library(googleVis)

Importing Datasets

Capital_Expenditure = read.csv('D:/study/datasets/eda assgnmnt/Capital_Expenditure.csv')#
crop_prod = read.csv('D:/study/datasets/eda assgnmnt/crop_production.csv')
gdp = read.csv('D:/study/datasets/eda assgnmnt/gdp.csv')
commodities = read.csv('D:/study/datasets/eda assgnmnt/india_commodities.csv')#
population = read.csv('D:/study/datasets/eda assgnmnt/India_population.csv')#
literacy = read.csv('D:/study/datasets/eda assgnmnt/literacy_rate.csv')#
inr_price = read_excel('D:/study/datasets/eda assgnmnt/Official exchange rate LCU per USD.xlsx')
total_reserves = read_excel('D:/study/datasets/eda assgnmnt/Total Reserves.xlsx')#

Change in the Population of India

pop = ggplot(population, aes(Year, Population)) + scale_x_continuous(breaks = c(1970:2018)) +
  theme_fivethirtyeight() + theme(axis.text.x = element_text(angle = 45, vjust = .6)) + geom_point() +
  geom_line(size = .8, color = 'black', alpha = .8) +
  labs(title = 'Population of India',
       x = 'Year',
       y = 'Population')
ggplotly(pop)

We can clearly see that India has crossed the 100 Crore mark in 1997. Also, there is a constant increase in the country’s population.

……………………………………………………………………………..

……………………………………………………………………………..

Literacy Rate of India.

colnames(literacy)[37] = 'Literacy Rate'
literacy_plot = ggplot(literacy, aes(Year, `Literacy Rate`)) +
  theme_economist_white() + theme(axis.text.x = element_text(angle = 45, vjust = .6)) + geom_point() +
  geom_line(size = .8, color = 'black') +
  labs(title = 'Literacy rate of India (According to Census)',
       x = 'Year',
       y = 'Literacy Rate')

ggplotly(literacy_plot)

Literacy rate in India has increased drastically in last 50 years. It has increased around 400%.

……………………………………………………………………………..

……………………………………………………………………………..

Capital Expenditure of India.

cap_exp = ggplot(Capital_Expenditure, aes(Year, Total)) +
  geom_bar(stat = 'Identity',width = .5, fill = 'springgreen3') + theme_tufte()+
  labs(title='Capital Expenditure of India (in million INR)',
       x='Year',
       y='Expenditure (million INR)')

ggplotly(cap_exp)

There is a significant increase in the Capital Expenditure of India. Since 1981, it has grown by 6200% till 2016.

……………………………………………………………………………..

……………………………………………………………………………..

Total Reserves of India (million USD)

res_plot = ggplot(total_reserves, aes(Year, India))+
  geom_bar(stat = 'Identity',width = .5, fill = 'coral3') + theme_economist()+
  labs(title='Total Reserves of India (million USD)',
       x='Year',
       y='Amount (million USD)')

ggplotly(res_plot)

There is a significant increase in the Total reserves of India as well. Since 1990, it has grown by 8000% till 2018.

……………………………………………………………………………..

……………………………………………………………………………..

Major Grocery Items

commodities$date = as.Date(commodities$date, '%d-%m-%Y')
commodities$Year = format(commodities$date, '%Y')

comm = commodities %>% group_by(Year, Commodity) %>%
  summarise(price = mean(Price.per.Kg, na.rm = TRUE)) %>% filter(!Commodity %in% c('Milk','Sunflower Oil (Packed)','Salt Pack (Iodised)','Tomato'))

comm$Year = as.Date(comm$Year, '%Y')

comm_plot = ggplot(comm, aes(Year,price)) + theme_igray() +
  geom_line(aes(color = Commodity), size = 0.8) +
  labs(title= 'Change in the Price of Major Grocery Items',
       x = 'Year',
       y = 'Price per Kg')

ggplotly(comm_plot)

Tea Loose(doubled) and Tur Dal(4 fold) (2 most consumed items in Indian Households) saw a significant increase in their prices in last 20 years. Rice and Onion also saw a 300% increase in their prices. Whereas price of Sugar is slightly increased.

……………………………………………………………………………..

……………………………………………………………………………..

Crop Production in India

crop = crop_prod  %>%  group_by(Crop_Year,Season, Crop) %>%
  summarise(Production = sum(Production, na.rm = TRUE))

major_crop = crop %>% dplyr::filter(Crop == 'Arhar/Tur'| 
                               Crop =='Bajra'| 
                               Crop == 'Rice'| 
                               Crop == 'Jowar' |
                               Crop == 'Maize'|
                               Crop == 'Wheat'|
                               Crop == 'Moong(Green Gram)'|
                               Crop == 'Ragi'|
                               Crop == 'Soyabean'|
                               Crop == 'Urad') %>% 
  group_by(Crop_Year, Crop) %>% 
  summarise(Production = sum(Production)) %>% dplyr::filter(Crop_Year != 2015)

crop_plot = ggplot(major_crop, aes(Crop_Year,Production)) + theme_pander() +
  geom_line(aes(color = Crop), size = 0.8) +
  labs(title= 'Production of Major Crops',
       x = 'Year',
       y = 'Production (Tonnes)')

ggplotly(crop_plot)

In India,food products made with Rice and Wheat are consumed on a daily basis, that is the reason behind their massive production.

other_crop = crop %>% dplyr::filter(Crop == 'Black pepper'| 
                               Crop =='Cardamom'| 
                               Crop == 'Cashewnut'| 
                               Crop == 'Coriander' |
                               Crop == 'Dry chillies'|
                               Crop == 'Ginger'|
                               Crop == 'Garlic'|
                               #Crop == 'Onion'|
                               #Crop == 'Potato'|
                               Crop == 'Turmeric') %>% 
  group_by(Crop_Year, Crop) %>% 
  summarise(Production = sum(Production)) %>% dplyr::filter(Crop_Year != 2015)

othr_crop_plot = ggplot(other_crop, aes(Crop_Year,Production)) + theme_classic() +
  geom_line(aes(color = Crop), size = 0.8) +
  labs(title= 'Production of Other Imp Crops',
       x = 'Year',
       y = 'Production (Tonnes)')

ggplotly(othr_crop_plot)

……………………………………………………………………………..

……………………………………………………………………………..

GDP

gdp$GDP =  as.numeric(gdp$GDP)

gdp_plot = ggplot(gdp, aes(Year,GDP)) + theme_solarized() +
  geom_line(size = 0.8, col = 'orangered2') +
  labs(title= 'GDP',
       x = 'Year',
       y = 'GDP (hundred crore INR)')
ggplotly(gdp_plot)

India’s GDP shows a gradual growth. It is estimated to perform consistently and steadily.

……………………………………………………………………………..

……………………………………………………………………………..

INR vs USD

inr = ggplot(inr_price, aes(Year,India)) + theme_solarized() +
  geom_point()+
  geom_line(size = 0.8, col = 'orangered2') +
  labs(title= 'Echange rate versus US Dollar',
       x = 'Year',
       y = 'Price')

ggplotly(inr)

Rupee is continuosly falling against US Dollar. Recently it broke the all time low mark and has crossed 71 rupee/dollar mark.

Comparision with neighbouring countries.

compare =  ggplot(inr_price, aes(Year)) + theme_solarized_2() + 
  geom_line(aes(y = Pakistan , col = 'Pakistan'), size = 0.8) + 
  geom_point(aes(y = Pakistan), color = 'blue') +
  geom_line(aes(y = India, col = 'India'), size = 0.8) + 
  geom_point(aes(y = India), color = 'darkgreen')+
  geom_line(aes(y = China, col = 'China'), size = .8) + 
  geom_point(aes(y = China), color = 'red') +
  geom_line(aes(y = `Sri Lanka`, col = 'Sri Lanka'), size = .8) + 
  geom_point(aes(y = `Sri Lanka`), color = 'purple') +
  theme(axis.text.x = element_text(angle = 0, vjust = .6),
        legend.title = element_blank()) +
  labs(title = 'Comparision with Neighbouring Countries (LCU vs USD)',
       x = 'Year',
       y = 'Price')

ggplotly(compare)

When we talk about India’s neighnours, China is the only country which has successfully managed to strong-arm their Currency against USD. Whereas currency of Pakistan and Sri-Lanka showed a staggering fall against USD. Sri Lankan Rupee (currency of Sri Lanka) suffered a huge 500% fall in last 20 years, it fell from 36 LCU in 1989 to 157 in 2018. Meanwhile, Pakistani Rupee (currency of Pakistan) tanked nearly 600%.